Out-of-Distribution Detection for Adaptive Computer Vision

Abstract

It is well known that computer vision can be unreliable when faced with previously unseen imaging conditions. This paper proposes a method to adapt camera parameters according to a normalizing flow-based out-of-distibution detector. A small-scale study is conducted which shows that adapting camera parameters according to this out-of-distibution detector leads to an average increase of 3 to 4 percentage points in mAP, mAR and F1 performance metrics of a YOLOv4 object detector. As a secondary result, this paper also shows that it is possible to train a normalizing flow model for out-of-distribution detection on the COCO dataset, which is larger and more diverse than most benchmarks for out-of-distibution detectors.

arXiv commentPublished in Springer Lecture Notes for Computer Science Vol. 13886 as part of the conference proceedings for Scandinavian Conference on Image Analysis 2023

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• YOLOv4: Optimal Speed and Accuracy of Object Detection
• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
• Generalized Out-of-Distribution Detection: A Survey
• A Survey of Uncertainty in Deep Neural Networks
• Safe Robot Navigation via Multi-Modal Anomaly Detection
• Embedded out-of-distribution detection on an autonomous robot platform